[PATCH 04/10] Use percpu buffers

[Pekka Enberg]

Hi Nitin,

On 8/10/10 8:32 AM, Nitin Gupta wrote:
> Other block drivers are allocating relatively small structs using
>>> mempool_alloc(). However, in case of zram, these buffers are quite
>>> large (compress_workmem is 64K!). So, allocating them on every write
>>> would probably be much slower than using a pre-allocated per-cpu buffer.
>>>        
>> The mempool API is precisely for that - using pre-allocated buffers instead of allocating every time. The preempt_disable() games make the code complex and have the downside of higher scheduling latencies so why not give mempools a try?
>>      
> mempool_alloc() first calls alloc_fn with ~(__GFP_WAIT | __GFP_IO)
> and *then* falls down to pre-allocated buffers. So, it will always
> be slower than directly using pre-allocated buffers as is done
> currently.
>
> One trick we can use is to have alloc_fn such that it always returns
> failure with ~__GFP_WAIT and do actual allocation otherwise. But still
> it seems like unnecessary cost.
>    
We can always extend the mempool API with mempool_prealloc() function if 
that turns out to be a problem. The per-CPU buffer with 
preempt_disable() trickery isn't really the proper thing to do here. It 
doesn't make much sense to disable preemption for compression that's 
purely CPU bound.

                     Pekka